Server definition

Hash: sha256:9e9e458363fafa4bea4e3d44af38ef1d8418d657dfa82db2f5d5e2da6de05bb6
What it is: What a remote MCP server returned when asked what it offers: 6 tools

The blob, as servednamed by its sha256

{
  "instructions": "NLP API suite with 5 text analysis capabilities:\n1. **Toxicity Detection** -- analyze_toxicity scores text for 6 harm categories.\n2. **Sentiment Analysis** -- analyze_sentiment classifies positive/negative tone.\n3. **Named Entity Recognition** -- extract_entities finds persons, orgs, locations.\n4. **PII Detection** -- detect_pii finds and optionally redacts personal information.\n5. **Language Detection** -- detect_language identifies language from 176 supported.\n\nAll tools accept plain text and return structured JSON.",
  "tools": [
    {
      "description": "Analyze text sentiment.\n\nReturns positive/negative classification with confidence scores.\nDistilBERT-based with sub-10ms latency. Multiple domain-specific\nmodel variants available.\n\nArgs:\n    text: Text to analyze for sentiment (positive/negative).\n    model: Model variant -- 'general' (default), 'financial', 'twitter'.\n\nReturns:\n    dict with keys:\n        - label (str): 'positive' or 'negative'\n        - score (float 0-1): Confidence score for the predicted label\n        - scores (dict): All label scores (positive, negative)",
      "inputSchema": {
        "properties": {
          "model": {
            "default": "general",
            "description": "Model variant: 'general' (default), 'financial', 'twitter'",
            "type": "string"
          },
          "text": {
            "description": "Text to analyze for sentiment (positive/negative)",
            "maxLength": 100000,
            "type": "string"
          }
        },
        "required": [
          "text"
        ],
        "type": "object"
      },
      "name": "analyze_sentiment",
      "outputSchema": null
    },
    {
      "description": "Analyze text for toxic content.\n\nReturns scores for 6 categories: toxic, severe_toxic, obscene, threat,\ninsult, identity_hate. Each score is 0.0-1.0.\nBERT-based classifier with sub-15ms latency on GPU.\n\nArgs:\n    text: Text to analyze for toxicity (hate speech, insults, threats).\n\nReturns:\n    dict with keys:\n        - toxic (float 0-1): Overall toxicity score\n        - severe_toxic (float 0-1): Severe toxicity score\n        - obscene (float 0-1): Obscenity score\n        - threat (float 0-1): Threat score\n        - insult (float 0-1): Insult score\n        - identity_hate (float 0-1): Identity-based hate score\n        - is_toxic (bool): Whether text exceeds toxicity threshold",
      "inputSchema": {
        "properties": {
          "text": {
            "description": "Text to analyze for toxicity (hate speech, insults, threats)",
            "maxLength": 100000,
            "type": "string"
          }
        },
        "required": [
          "text"
        ],
        "type": "object"
      },
      "name": "analyze_toxicity",
      "outputSchema": null
    },
    {
      "description": "Check health status of NLP API services and loaded models.\n\nReturns:\n    dict with keys:\n        - status (str): 'healthy' or error state\n        - models (dict): Loaded model status per capability\n        - version (str): API version",
      "inputSchema": {
        "properties": {},
        "type": "object"
      },
      "name": "check_nlp_service",
      "outputSchema": null
    },
    {
      "description": "Detect the language of text.\n\nSupports 176 languages using fastText. Sub-1ms inference latency.\nReturns ISO 639-1 codes with confidence scores.\n\nArgs:\n    text: Text to identify the language of.\n    top_k: Number of top language predictions to return (default: 3).\n\nReturns:\n    dict with keys:\n        - language (str): Top predicted language ISO 639-1 code\n        - confidence (float 0-1): Confidence for top prediction\n        - predictions (list): Top-k predictions, each with:\n            - language (str): ISO 639-1 code\n            - confidence (float 0-1): Prediction confidence",
      "inputSchema": {
        "properties": {
          "text": {
            "description": "Text to identify the language of",
            "maxLength": 100000,
            "type": "string"
          },
          "top_k": {
            "default": 3,
            "description": "Number of top language predictions to return",
            "type": "integer"
          }
        },
        "required": [
          "text"
        ],
        "type": "object"
      },
      "name": "detect_language",
      "outputSchema": null
    },
    {
      "description": "Detect personally identifiable information (PII) in text.\n\nFinds emails, phone numbers, SSNs, credit cards, IP addresses, and\nperson names. Optionally returns redacted text with PII replaced by\ntype labels (e.g. [EMAIL], [PHONE]). BERT-NER + regex ensemble.\n\nArgs:\n    text: Text to scan for personally identifiable information.\n    redact: If true, return redacted text with PII replaced by [TYPE].\n\nReturns:\n    dict with keys:\n        - pii_found (list): Detected PII items, each containing:\n            - text (str): The PII value found\n            - type (str): PII type (EMAIL, PHONE, SSN, CREDIT_CARD, IP, PERSON)\n            - start (int): Character offset start\n            - end (int): Character offset end\n            - score (float 0-1): Detection confidence\n        - count (int): Total PII items found\n        - redacted_text (str|null): Text with PII replaced (when redact=true)\n        - has_pii (bool): Whether any PII was detected",
      "inputSchema": {
        "properties": {
          "redact": {
            "default": false,
            "description": "If true, return redacted text with PII replaced by [TYPE]",
            "type": "boolean"
          },
          "text": {
            "description": "Text to scan for personally identifiable information",
            "maxLength": 100000,
            "type": "string"
          }
        },
        "required": [
          "text"
        ],
        "type": "object"
      },
      "name": "detect_pii",
      "outputSchema": null
    },
    {
      "description": "Extract named entities (NER) from text.\n\nIdentifies persons, organizations, locations, and miscellaneous entities\nwith span offsets and confidence scores. BERT-NER based with sub-50ms latency.\n\nArgs:\n    text: Text to extract named entities from.\n\nReturns:\n    dict with keys:\n        - entities (list): Detected entities, each containing:\n            - text (str): Entity text\n            - label (str): Entity type (PER, ORG, LOC, MISC)\n            - start (int): Character offset start\n            - end (int): Character offset end\n            - score (float 0-1): Confidence score\n        - count (int): Total number of entities found",
      "inputSchema": {
        "properties": {
          "text": {
            "description": "Text to extract named entities from (persons, organizations, locations)",
            "maxLength": 100000,
            "type": "string"
          }
        },
        "required": [
          "text"
        ],
        "type": "object"
      },
      "name": "extract_entities",
      "outputSchema": null
    }
  ]
}

Verify it yourself

curl -s https://api.teppi.xyz/v1/evidence/sha256:9e9e458363fafa4bea4e3d44af38ef1d8418d657dfa82db2f5d5e2da6de05bb6 | sha256sum